Semantic role labeling of prepositional phrases

Authors:
Patrick Ye;Timothy Baldwin
Affiliations:
University of Melbourne, Australia;University of Melbourne, Australia
Venue:
ACM Transactions on Asian Language Information Processing (TALIP)
Year:
2006

Citing 7
Cited 7

WordNet: a lexical database for English

Communications of the ACM
A maximum entropy approach to natural language processing

Computational Linguistics
Building a large annotated corpus of English: the penn treebank

Computational Linguistics - Special issue on using large corpora: II
A maximum-entropy-inspired parser

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Representing text chunks

EACL '99 Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics
Preposition semantic classification via Penn Treebank and FrameNet

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Semantic role labeling via integer linear programming inference

COLING '04 Proceedings of the 20th international conference on Computational Linguistics

Prepositions in applications: A survey and introduction to the special issue

Computational Linguistics
Exploiting semantic role resources for preposition disambiguation

Computational Linguistics
Towards automatic animated storyboarding

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 1
MELB-YB: preposition sense disambiguation using rich semantic features

SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Joint learning of preposition senses and semantic roles of prepositional phrases

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Models and training for unsupervised preposition sense disambiguation

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Exploiting frame information for prepositional phrase semantic role labeling

AI'10 Proceedings of the 23rd Canadian conference on Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a method for labelling prepositional phrases according to two different semantic role classifications, as contained in the Penn treebank and the CoNLL 2004 Semantic Role Labeling data set. Our results illustrate the difficulties in determining preposition semantics, but also demonstrate the potential for PP semantic role labelling to improve the performance of a holistic semantic role labelling system.